Job Responsibilities
1. Develop and optimize deep learning-based feature point detection and matching algorithms (e.g., SuperPoint, Lightglue);
2. Implement or enhance feature modules in existing SLAM systems using frameworks like PyTorch/TensorFlow;
3. Collaborate with the team to deploy algorithms on platforms such as NX/RK3588 and conduct performance testing;
4. Track cutting-edge research papers, reproduce or optimize relevant learning-based feature point detection and matching algorithms;
Job Requirements
1. Bachelor's degree or higher in Computer Science, Automation, Electronics, or related fields;
2. Proficient in 3D vision, SLAM, machine learning algorithms, and skilled in using open-source machine learning libraries;
3. Familiar with learning-based feature point extraction and matching algorithms such as SuperPoint, LightGlue, DISK, and SuperGlue.
4. Strong teamwork and communication skills;
Preferred Qualifications
1. Knowledge of model acceleration techniques like TensorRT and ONNX.
2. Familiarity with open-source SLAM frameworks such as VINS-Fusion, ORB-SLAM3, SVO, and MSCKF.
We Offer
1. Growth Platform: Participate in cutting-edge R&D alongside senior experts and cross-disciplinary teams to rapidly enhance professional capabilities;
2. Hands-on opportunities: Direct involvement in UAV system development and application deployment, experiencing the full journey from algorithm to product;
3. Incentive structure: Outstanding interns may receive full-time conversion opportunities and participate in more core projects in the future;
4. Work environment: An open, inclusive, and dynamic team atmosphere providing a broad stage for your innovation.
